Contract
{
"type": "object",
"required": [
"text"
],
"properties": {
"text": {
"type": "string",
"description": "Text to analyze"
}
},
"additionalProperties": false
}{
"type": "object",
"properties": {
"scores": {
"type": "object",
"properties": {
"neutral": {
"type": "number"
},
"negative": {
"type": "number"
},
"positive": {
"type": "number"
}
},
"description": "Positive/negative/neutral breakdown, observed summing to 1 on both calls.",
"additionalProperties": true
},
"aspects": {
"type": "array",
"items": {
"type": "object",
"properties": {
"aspect": {
"type": "string",
"description": "Short topic label, e.g. 'food quality'."
},
"sentiment": {
"type": "string",
"description": "This aspect's own sentiment label."
},
"text_span": {
"type": "string",
"description": "The exact substring of the input text that supports this aspect."
}
},
"additionalProperties": true
},
"description": "One entry per distinct topic the text discusses (2 entries on the product review, 3 on the mixed restaurant feedback) -- not a fixed count."
},
"summary": {
"type": "string",
"description": "A one-to-two sentence plain-language summary of the analysis."
},
"sentiment": {
"type": "string",
"description": "Overall label observed as 'positive' and 'mixed' across the two real calibration calls; the endpoint's own description also documents 'negative' and 'neutral' as possible values, neither observed yet."
},
"confidence": {
"type": "number",
"description": "0-1. 0.98 on an unambiguous positive review, 0.92 on a mixed one."
},
"detected_language": {
"type": "string",
"description": "e.g. 'English'. Observed as a full language name, not an ISO code."
}
},
"description": "The sentiment record, as returned at routing.responseResultPath ($.output).",
"additionalProperties": true
}Pricing
Every real charge, itemised. A model that quietly omits one is a slow financial leak, so nothing here is rolled up, and a charge that only applies to some inputs says so rather than being added in.
Prices in this catalog are the provider's own list price, not your bill: Omnial MCP charges provider cost plus a platform markup on top, so what you are charged is higher than the figure shown. For the exact amount a specific call will cost, run omnial_execute with dry_run: true; that number includes the markup and is what we hold while the call runs. It is a quote, not a cap on the charge.
| Charge | Rate |
|---|---|
Per call Flat, regardless of what comes back | $0.081082365 |
- Cost basis
- Not recorded
This tool's catalog entry does not record how its final bill is determined, so we will not tell you whether its cost is fixed before the call or reported by the provider afterwards. Either way what is held is a quote rather than a cap: you are charged what the call actually costs, bounded at 2x the quote.
- Updated
- Sep 23, 2026
